Gemma 3 4B Pt — Hardware Requirements & GPU Compatibility
VisionGemma 3 4B PT represents Google's pretrained checkpoint at the lower end of the Gemma 3 family, containing roughly 4.3 billion parameters when vision components are included. This model employs a vision-language architecture capable of handling both text and images. The "PT" suffix indicates its status as a base model: it lacks instruction tuning and cannot reliably follow chat prompts, making it suitable for fine-tuning, research, or experimentation instead of direct use as an assistant. Given its size, the quantized version runs on nearly any recent GPU or even a CPU, though the instruction-tuned release remains the better choice for actual conversation. Similar to the larger Gemma 3 models, it supports a context window of up to 128K tokens. Distribution follows the Gemma Terms of Use, and users must acknowledge this license on Hugging Face to gain access. Released in February 2025, it stands as one of the smaller pretrained options within the Gemma 3 lineup, sitting alongside the 12B and 27B variants.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~231 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~25 tok/s)
Gemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 3 4B Pt
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/mradermacher/gemma-3-4b-pt-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 19.0 GB free · 16K context
Download: gemma-3-4b-pt.Q4_K_M.gguf2.49 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3060 12GB (7 GB headroom) · Q4_K_M
- Generation speed
- ~82 tok/s
- generation speed
- Cost per 1M output tokens
- $0.21
- per 1M output tokens
How Much VRAM Does Gemma 3 4B Pt Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.0 GB | 6.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~326 tok/s | |
| 2.1 GB | 6.7 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~317 tok/s | |
| 2.3 GB | 6.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~284 tok/s | |
| 2.4 GB | 7 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~277 tok/s | |
| 2.8 GB | 7.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~231 tok/s | |
| 3.4 GB | 8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~194 tok/s | |
| 3.9 GB | 8.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~168 tok/s | |
| 4.7 GB | 9.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~139 tok/s |
Selected Q4_K_M
4-bit medium quantization5.0GBat 16K context
- Weights
- 2.2 GB
- KV cache
- 2.5 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Gemma 3 4B Pt?
Q4_K_M · 2.8 GBGemma 3 4B Pt (Q4_K_M) requires 2.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce GTX 1650 SUPER. 185 devices with unified memory can run Gemma 3 4B Pt, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).
12 GB
12 GB tier →fits · 7.0 GB free · up to 32K ctx
16 GPUs · 1 device family
RTX 3080 Ti~209Simulate output on RTX 3080 TiRTX 3080 12GB~209Simulate output on RTX 3080 12GBRTX 5070~154Simulate output on RTX 5070iPhone~19Simulate output on Apple iPhone 17 Pro20 GB
fits · 15.0 GB free · up to 32K ctx
1 GPU
RX 7900 XT~169Simulate output on RX 7900 XT32–40 GB
fits · 27.0 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~410Simulate output on RTX 5090M5 Max*36 GB~113Simulate output on Mac Studio M5 Max (36 GB)M632 GB~42Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~69Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~47Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Gemma 3 4B Pt
Gemma 3 family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Spark X2.6 4BXHToken | — | 4.3 GB | ~221 | same size |
| Granite Vision 4.1 4BIBM | — | 4 GB | ~228 | same size |
| Qwen3 VL 4B InstructAlibaba | — | 4.5 GB | ~208 | same size |
| MiniCPM V 4OpenBMB | — | 3.1 GB | ~236 | same size |
| Phi 3.5 Vision InstructMicrosoft | — | 9.2 GB | ~183 | same size |
| NVIDIA Nemotron 3.5 Bolt E4B 4GBNVIDIA | — | 4.8 GB | ~248 | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- Family
- Gemma 3
- Parameters
- 4.3B
- Release Date
- 2025-02-20
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Gemma 3 4B Pt need?
Gemma 3 4B Pt requires 2.8 GB of VRAM at Q4_K_M, or 9.5 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 4.3B × 4.8 bits ÷ 8 = 2.6 GB
KV Cache + Overhead ≈ 0.2 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
What's the best quantization for Gemma 3 4B Pt?
For Gemma 3 4B Pt, Q4_K_M (2.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (3.3 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 3 4B Pt on a Mac?
Yes — Mac Mini M2 (8 GB) and 158 other Macs can run Gemma 3 4B Pt. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Gemma 3 4B Pt locally?
Yes — Gemma 3 4B Pt can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 3 4B Pt?
At Q4_K_M, Gemma 3 4B Pt can reach ~1690 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~231 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 2.84 × 0.65 = ~1831 tok/s
Estimated speed at Q4_K_M (2.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Gemma 3 4B Pt?
At Q4_K_M, the download is about 2.58 GB. The full-precision BF16 version is 8.60 GB. The smallest option (IQ2_XXS) is 1.18 GB.
Which GPUs can run Gemma 3 4B Pt?
114 consumer GPUs can run Gemma 3 4B Pt at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB, NVIDIA GeForce GTX 1050 Ti. 107 GPUs have plenty of headroom for comfortable inference.
Which devices can run Gemma 3 4B Pt?
185 devices with unified memory can run Gemma 3 4B Pt at Q4_K_M (2.8 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.